Building Business Applications for Office 365 SharePoint Online using Azure Machine Learning - SharePoint Fest Chicago 2017

WithumSmith+Brown, PC | BE IN A POSITION OF STRENGTH
1
SM
@pgbhoyar #SPFestChicago
Prashant G Bhoyar MVP
SharePoint Fest, Chicago, IL http://www.sharepointfest.com/Chicago
08 December 2017
Building Business Applications for Office 365/
SharePoint Online using Azure Machine Learning

2
SM
Who AM I ?
• Born and raised in India
• Came to United States of America in 2007 for studies
• University of Maryland College Park Alumni
• Co-Author of the book “PowerShell for Office 365”
• Technical Reviewer of the book “Pro : SharePoint 2013 Administration”
• Organizer of SharePoint Saturday Baltimore (SPSBMORE)
➢ http://www.spsevents.org/city/baltimore/baltimoretecc
• Organizer of SharePoint Saturday DC ( SPSDC )
➢ http://www.spsevents.org/city/DC/summer2017
• Founder and Organizer of DC-Metro Office 365 User Group
➢ Monthly in person & online event
➢ http://www.meetup.com/DC-Metro-Office-365-User-Group/
• Recipient of Antarctic Service Medal
• Microsoft MVP ( Most Valuable Professional)
• Solution Architect at Withum Smith and Brown PC
➢ https://digital.withum.com
➢ Former Portal Solutions
➢ Focus on Microsoft Solutions and Services
➢ Work in Bethesda, Maryland Office
Prashant G Bhoyar
(PGB)

3
SM
Withum Microsoft Solutions and Services
3
• Modern workplace
• Office 365 Implementations/
Migrations
• Turnkey Intranet Solution
• Managed Services
• Data Analytics
• Enterprise Mobility + Security
• Business Process Automation
• Dynamics 365
• Azure

4
SM
• 100 Level Session
• Approach
• What is Machine Learning?
• Azure Machine Learning Studio
• How to get started?
• Demos
• Key Takeaways
• Q&A
Agenda

5
SM

6
SM
Audience Poll
▪ How many of you are IT pros?
▪ How many of you are Developers?
▪ How many of you are Power Users?
▪ How many of you are Data Scientist?
▪ How many of you are using Azure Machine Learning Studio?
6

7
SM

8
SM
Why We Should invest time to learn AI?
▪ Because of the advancements in the computation, tech industry is focusing on
using AI in business applications
▪ I think right now it is at the same state as mobile development was when iPhone
1 was first launched
▪ I think in next 2-3 year, AI & ML will be mainstream
▪ Amazon sold “Millions” of Alexa devices during this holiday season
• https://techcrunch.com/2017/11/28/amazon-sold-millions-of-alexa-devices-over-the-
holiday-shopping-weekend/
▪ You don’t need to be a Data Scientist to use Machine Learning ☺
• Analogy : JavaScript Frameworks
8

9
SM

10
SM
Approach
▪ This session is geared towards Non-Data Scientist ☺
▪ Target Audience is Developers/IT Pros and Power Users
10

11
SM
11

12
SM
12

13
SM
13

14
SM
14

15
SM
15

16
SM
Microsoft AI Platform
16

17
SM
17

18
SM
18

19
SM
19

20
SM
What is Machine Learning?

21
SM
What is Machine Learning?
▪ It examines large amounts of data looking for patterns, then
generates code that lets you recognize those patterns in new
data.
▪ Your applications can use this generated code to make better
predictions.
▪ It can help you create smarter applications.
21

22
SM
Machine Learning in a Nutshell
Machine
learning
algorithm
Model
Application
Data
Contains
patterns
Finds
patterns
Recognizes
patterns
Provides new data to
see if it matches
known patterns

23
SM
Deploy
chosen
model
Chosen
Model
Apply
learning
algorithm
to data
Candidate
Model
The Machine Learning Process
Prepared
Data
Apply pre-
processing
to data
Iterate to find the
best model
Data
Preprocessing
Modules
Iterate until data
is ready
Preprocessing
Modules
Machine
Learning
Algorithms
Applications
The goal:
Smarter
applications
Raw
Data
Raw
Data
Choose
data

24
SM
Terminology
Training data
The prepared data used to create
a model
Creating a model is called
training a model
Supervised learning
The value you want to predict
is in the training data
The data is labeled
Unsupervised learning
The value you want to predict is not
in the training data
The data is unlabeled
The most common
approach

25
SM
Styles of Machine Learning Algorithms Examples
Decision tree Neural network Bayesian K-means
P(A) P(B|A)
P(B)
P(A|B) =
Deep learning
uses this

26
SM
@pgbhoyar #SPFestChicagoSource : https://docs.microsoft.com/en-us/azure/machine-learning/studio/algorithm-cheat-sheet

27
SM
What is deep learning
--- Yoshua Bengio
Machine learning is a way to try to make machines intelligent by allowing computers to
learn from examples about the world around us or about some specific aspect of it.
Deep learning is an approach to machine learning, particular among all the machine
learning methods in that it is inspired by some of the things we know about the brain.
It’s trying to make computers learn multiple levels of abstraction and representation,
which is presumably what makes these systems so successful
Reinforcement learning is a type of machine learning where the learner doesn’t get to
know what a human would do in this context. The learner only gets to see if the actions
were good or bad after a long set of actions. A lot of the recent progress in this area is
in things like playing games, but reinforcement learning probably is going to be very
important for things like self-driving cars.

28
SM
Machine Learning: Practical Applications
▪ Spam & Fraud Detection
▪ Decision Engines: Approval or Disapproval
▪ Recommendation Engines: Which one to choose
▪ Predictive Maintenance
▪ Optical Character Recognition (OCR)
▪ Natural Language Processing
▪ Machine Translation
▪ Autonomous Systems (Robotics)

29
SM
Machine Learning: Practical Applications
▪ Recommendation Engines :
• Training Needs,
• Resourcing Needs,
• Process Improvements
▪ Text Analysis
• Product Reviews
• Case / Document Classification
• Social Media Analytics
• Intellectual Property
• Plagiarism Check
• Sentiment Analysis

30
SM
Text Analytics API
▪ Analyze unstructured text for tasks
• Language detection
• Key phrase extraction
• Sentiment Analysis
▪ Sentiment analysis is the process of detecting whether a piece
of Writing is positive, negative or neutral
▪ Return a numeric score between 0 and 1
• Negative 0…1 Positive sentiment
▪ Advanced natural language processing
• https://azure.microsoft.com/en-us/services/cognitive-services/text-
analytics/
30

31
SM

32
SM
What is Azure Machine Learning Studio?
▪ A fully-managed cloud service that enables you to easily build,
deploy, and share predictive analytics solutions.
▪ It has everything you need to create complete predictive analytics
solutions in the cloud, from a large algorithm library, to a studio for
building models, to an easy way to deploy your model as a web
service
▪ Quickly create, test, operationalize, and manage predictive models
▪ Publish as Web Service
32

33
SM
Demo

34
SM
▪ Sign up for Office 365 Developer
Program at http://dev.office.com/
▪ Get 1 year of Office 365
subscription for free
▪ Excellent for personal
development use
▪ 1 Month Trial
▪ https://products.office.com/en-
us/business/compare-office-365-
for-business-plans
34
How to get personal Office 365
Developer Tenant?

35
SM

36
SM
36
How to get personal Azure Subscription?
▪ If you have MSDN Enterprise subscription
▪ You can get $150/month Azure credits for free
▪ Sign Up for Free trial :
https://azure.microsoft.com/
▪ Credit Card is required
▪ Microsoft Imagine
▪ Former Dreamspark
▪ No credit card required
▪ Valid .edu account from participating
school/institution
▪ Limited feature sets

37
SM
• Approach
• What is Machine Learning?
• Azure Machine Learning Studio
• How to get started?
• Demos
Recap

38
SM
Other SPFest Chicago 2017 AI/ML Session
▪ SRC 205 - Modern Collaboration with AI
38

39
SM
Key Takeaways
▪ Hopefully the contents we covered today made you to explore
Azure Machine Learning Studio and you will go home and play
with it ☺
• https://studio.azureml.net/
▪ Sign up for Developer Program using https://dev.office.com/
▪ Spend some time doing research before investing time to
learn/explore new product/services

40
SM
References
▪ https://studio.azureml.net/
▪ https://azure.microsoft.com/en-us/services/cognitive-services/text-analytics/
▪ https://docs.microsoft.com/en-us/azure/machine-learning/studio/algorithm-cheat-sheet

41
SM
Q&A

42
SM
Event Eval

43
SM
Questions? Feedback? Contact me:
▪ Email: pgbhoyar@gmail.com
▪ Twitter: @PGBhoyar
▪ Blog: http://pgbhoyar.com
▪ LinkedIn: https://www.linkedin.com/in/pgbhoyar/
▪ Slides :https://www.slideshare.net/pgbhoyar
▪ Free Consulting/ Q&A: https://pgbhoyar.com/free-question-answer-session/
▪ Feedback : Please provide feedback
▪ Event App
▪ Email
Thank You
Organizers, Sponsors and You for Making this Possible.

Building Business Applications for Office 365 SharePoint Online using Azure Machine Learning - SharePoint Fest Chicago 2017

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to Building Business Applications for Office 365 SharePoint Online using Azure Machine Learning - SharePoint Fest Chicago 2017

Similar to Building Business Applications for Office 365 SharePoint Online using Azure Machine Learning - SharePoint Fest Chicago 2017 (20)

More from Prashant G Bhoyar (Microsoft MVP)

More from Prashant G Bhoyar (Microsoft MVP) (8)

Recently uploaded

Recently uploaded (20)

Building Business Applications for Office 365 SharePoint Online using Azure Machine Learning - SharePoint Fest Chicago 2017